62 |
63 |
117 |
118 |
119 |
120 |
121 |
122 |
153 |
154 |
155 |
156 |
157 |
158 |
159 |
160 |
161 |
--------------------------------------------------------------------------------
/docs/articles/index.html:
--------------------------------------------------------------------------------
1 |
2 |
3 |
4 |
5 |
6 |
7 |
8 |
9 |
123 |
139 |
140 |
141 |
142 |
152 |
124 |
131 |
132 |
137 |
138 |
125 |
127 |
128 | Content not found. Please use links in the navbar.
129 |
130 | Page not found (404)
126 |
62 |
63 |
117 |
118 |
119 |
120 |
121 |
122 |
152 |
153 |
154 |
155 |
156 |
157 |
158 |
159 |
160 |
--------------------------------------------------------------------------------
/docs/articles/youtubecaption_vignette.html:
--------------------------------------------------------------------------------
1 |
2 |
3 |
4 |
5 |
6 |
7 |
8 |
123 |
139 |
140 |
141 |
151 |
124 |
138 |
125 |
127 |
128 | Articles
126 |
129 |
137 | All vignettes
130 | 131 | 132 |-
133 |
- How to Use Youtubecaption 134 |
- 135 |
23 |
78 |
79 |
80 |
81 |
82 |
190 |
191 |
192 |
193 |
194 |
195 |
196 |
--------------------------------------------------------------------------------
/docs/articles/youtubecaption_vignette_files/header-attrs-2.0.5/header-attrs.js:
--------------------------------------------------------------------------------
1 | // Pandoc 2.9 adds attributes on both header and div. We remove the former (to
2 | // be compatible with the behavior of Pandoc < 2.8).
3 | document.addEventListener('DOMContentLoaded', function(e) {
4 | var hs = document.querySelectorAll("div.section[class*='level'] > :first-child");
5 | var i, h, a;
6 | for (i = 0; i < hs.length; i++) {
7 | h = hs[i];
8 | if (!/^h[1-6]$/i.test(h.tagName)) continue; // it should be a header h1-h6
9 | a = h.attributes;
10 | while (a.length > 0) h.removeAttribute(a[0].name);
11 | }
12 | });
13 |
--------------------------------------------------------------------------------
/docs/articles/youtubecaption_vignette_files/header-attrs-2.1.3/header-attrs.js:
--------------------------------------------------------------------------------
1 | // Pandoc 2.9 adds attributes on both header and div. We remove the former (to
2 | // be compatible with the behavior of Pandoc < 2.8).
3 | document.addEventListener('DOMContentLoaded', function(e) {
4 | var hs = document.querySelectorAll("div.section[class*='level'] > :first-child");
5 | var i, h, a;
6 | for (i = 0; i < hs.length; i++) {
7 | h = hs[i];
8 | if (!/^h[1-6]$/i.test(h.tagName)) continue; // it should be a header h1-h6
9 | a = h.attributes;
10 | while (a.length > 0) h.removeAttribute(a[0].name);
11 | }
12 | });
13 |
--------------------------------------------------------------------------------
/docs/authors.html:
--------------------------------------------------------------------------------
1 |
2 |
3 |
4 |
5 |
6 |
7 |
8 |
9 |
83 |
177 |
178 |
179 |
180 |
189 |
84 |
169 |
170 |
175 |
176 |
85 |
92 |
93 |
94 |
95 |
96 |
97 | How to Use Youtubecaption
86 |JooYoung Seo
87 | 88 |2020-05-15
89 | 90 | Source:vignettes/youtubecaption_vignette.Rmd
91 | youtubecaption_vignette.Rmd
98 |
168 | 99 | youtubecaption
100 | 101 |
103 |
107 | 104 | Motivation
105 |Although there exist some R packages tailored for YouTube API (e.g., ‘tuber’), downloading YouTube video subtitle (i.e., caption) in a tidy form has never been a low-hanging fruit. Using ‘youtube-transcript-api’ Python package under the hood, this R package provides users with a convenient way of parsing and converting a desired YouTube caption into a handy tibble data_frame object. Furthermore, users can easily save a desired YouTube caption data as a tidy Excel file without advanced programming background knowledge.
106 |
108 |
138 | 109 | Installation
110 |
111 |
117 |
121 | 112 | Python Dependencies
113 |youtubecaption requires Anaconda Python environment on your system Path.
If you have not installed Conda environment on your system, please download and install Anaconda (Python 3.6 or later is recommended).
115 |For this package, I have employed youtube-transcript-api Python module into R using reticulate.
116 |
122 |
130 |
131 | 123 | Development Version
124 |You can install the latest development version as follows:
125 |if(!require(remotes)) { 126 | install.packages("remotes") 127 | } 128 | 129 | remotes::install_github("jooyoungseo/youtubecaption")
132 |
136 |
137 | 133 | Stable Version
134 |You can install the released version of youtubecaption from CRAN with:
135 |install.packages('youtubecaption')
139 |
166 |
167 | 140 | Usage
141 |Please use get_caption() function after loading youtubecaption package like below:
library(youtubecaption) 143 | 144 | # Let's get the video caption out of Hadley Wickham's "You can't do data science in a GUI": 145 | url <- "https://www.youtube.com/watch?v=cpbtcsGE0OA" 146 | caption <- get_caption(url) 147 | caption 148 | 149 | #> # A tibble: 1,420 x 5 150 | #> segment_id text start duration vid 151 | #> <int> <chr> <dbl> <dbl> <chr> 152 | #> 1 1 thank you for coming to a meeting ~ 7.13 8.32 cpbtcsGE0~ 153 | #> 2 2 in regards to data science GUI with 10.7 8.44 cpbtcsGE0~ 154 | #> 3 3 happy with chief data scientist in~ 15.4 7.11 cpbtcsGE0~ 155 | #> 4 4 studio as well as the member of th~ 19.1 7.23 cpbtcsGE0~ 156 | #> 5 5 Foundation and an attempt professo~ 22.6 6 cpbtcsGE0~ 157 | #> 6 6 Stanford and at the University of 26.4 6.48 cpbtcsGE0~ 158 | #> 7 7 Auckland he builds both computatio~ 28.6 7.17 cpbtcsGE0~ 159 | #> 8 8 and cognitive tools to make data s~ 32.8 7.5 cpbtcsGE0~ 160 | #> 9 9 easier faster and more times his w~ 35.7 7.01 cpbtcsGE0~ 161 | #> 10 10 includes various packages as well ~ 40.4 6.21 cpbtcsGE0~ 162 | #> # ... with 1,410 more rows 163 | 164 | # Save the caption as an Excel file and open it right it away: 165 | get_caption(url = url, savexl = TRUE, openxl = TRUE)
`, then ``, etc.) that has more than one element. Defaults to 1 (for ``).
76 | getTopLevel: function($scope) {
77 | for (var i = 1; i <= 6; i++) {
78 | var $headings = this.findOrFilter($scope, 'h' + i);
79 | if ($headings.length > 1) {
80 | return i;
81 | }
82 | }
83 |
84 | return 1;
85 | },
86 |
87 | // returns the elements for the top level, and the next below it
88 | getHeadings: function($scope, topLevel) {
89 | var topSelector = 'h' + topLevel;
90 |
91 | var secondaryLevel = topLevel + 1;
92 | var secondarySelector = 'h' + secondaryLevel;
93 |
94 | return this.findOrFilter($scope, topSelector + ',' + secondarySelector);
95 | },
96 |
97 | getNavLevel: function(el) {
98 | return parseInt(el.tagName.charAt(1), 10);
99 | },
100 |
101 | populateNav: function($topContext, topLevel, $headings) {
102 | var $context = $topContext;
103 | var $prevNav;
104 |
105 | var helpers = this;
106 | $headings.each(function(i, el) {
107 | var $newNav = helpers.generateNavItem(el);
108 | var navLevel = helpers.getNavLevel(el);
109 |
110 | // determine the proper $context
111 | if (navLevel === topLevel) {
112 | // use top level
113 | $context = $topContext;
114 | } else if ($prevNav && $context === $topContext) {
115 | // create a new level of the tree and switch to it
116 | $context = helpers.createChildNavList($prevNav);
117 | } // else use the current $context
118 |
119 | $context.append($newNav);
120 |
121 | $prevNav = $newNav;
122 | });
123 | },
124 |
125 | parseOps: function(arg) {
126 | var opts;
127 | if (arg.jquery) {
128 | opts = {
129 | $nav: arg
130 | };
131 | } else {
132 | opts = arg;
133 | }
134 | opts.$scope = opts.$scope || $(document.body);
135 | return opts;
136 | }
137 | },
138 |
139 | // accepts a jQuery object, or an options object
140 | init: function(opts) {
141 | opts = this.helpers.parseOps(opts);
142 |
143 | // ensure that the data attribute is in place for styling
144 | opts.$nav.attr('data-toggle', 'toc');
145 |
146 | var $topContext = this.helpers.createChildNavList(opts.$nav);
147 | var topLevel = this.helpers.getTopLevel(opts.$scope);
148 | var $headings = this.helpers.getHeadings(opts.$scope, topLevel);
149 | this.helpers.populateNav($topContext, topLevel, $headings);
150 | }
151 | };
152 |
153 | $(function() {
154 | $('nav[data-toggle="toc"]').each(function(i, el) {
155 | var $nav = $(el);
156 | Toc.init($nav);
157 | });
158 | });
159 | })();
160 |
--------------------------------------------------------------------------------
/docs/docsearch.css:
--------------------------------------------------------------------------------
1 | /* Docsearch -------------------------------------------------------------- */
2 | /*
3 | Source: https://github.com/algolia/docsearch/
4 | License: MIT
5 | */
6 |
7 | .algolia-autocomplete {
8 | display: block;
9 | -webkit-box-flex: 1;
10 | -ms-flex: 1;
11 | flex: 1
12 | }
13 |
14 | .algolia-autocomplete .ds-dropdown-menu {
15 | width: 100%;
16 | min-width: none;
17 | max-width: none;
18 | padding: .75rem 0;
19 | background-color: #fff;
20 | background-clip: padding-box;
21 | border: 1px solid rgba(0, 0, 0, .1);
22 | box-shadow: 0 .5rem 1rem rgba(0, 0, 0, .175);
23 | }
24 |
25 | @media (min-width:768px) {
26 | .algolia-autocomplete .ds-dropdown-menu {
27 | width: 175%
28 | }
29 | }
30 |
31 | .algolia-autocomplete .ds-dropdown-menu::before {
32 | display: none
33 | }
34 |
35 | .algolia-autocomplete .ds-dropdown-menu [class^=ds-dataset-] {
36 | padding: 0;
37 | background-color: rgb(255,255,255);
38 | border: 0;
39 | max-height: 80vh;
40 | }
41 |
42 | .algolia-autocomplete .ds-dropdown-menu .ds-suggestions {
43 | margin-top: 0
44 | }
45 |
46 | .algolia-autocomplete .algolia-docsearch-suggestion {
47 | padding: 0;
48 | overflow: visible
49 | }
50 |
51 | .algolia-autocomplete .algolia-docsearch-suggestion--category-header {
52 | padding: .125rem 1rem;
53 | margin-top: 0;
54 | font-size: 1.3em;
55 | font-weight: 500;
56 | color: #00008B;
57 | border-bottom: 0
58 | }
59 |
60 | .algolia-autocomplete .algolia-docsearch-suggestion--wrapper {
61 | float: none;
62 | padding-top: 0
63 | }
64 |
65 | .algolia-autocomplete .algolia-docsearch-suggestion--subcategory-column {
66 | float: none;
67 | width: auto;
68 | padding: 0;
69 | text-align: left
70 | }
71 |
72 | .algolia-autocomplete .algolia-docsearch-suggestion--content {
73 | float: none;
74 | width: auto;
75 | padding: 0
76 | }
77 |
78 | .algolia-autocomplete .algolia-docsearch-suggestion--content::before {
79 | display: none
80 | }
81 |
82 | .algolia-autocomplete .ds-suggestion:not(:first-child) .algolia-docsearch-suggestion--category-header {
83 | padding-top: .75rem;
84 | margin-top: .75rem;
85 | border-top: 1px solid rgba(0, 0, 0, .1)
86 | }
87 |
88 | .algolia-autocomplete .ds-suggestion .algolia-docsearch-suggestion--subcategory-column {
89 | display: block;
90 | padding: .1rem 1rem;
91 | margin-bottom: 0.1;
92 | font-size: 1.0em;
93 | font-weight: 400
94 | /* display: none */
95 | }
96 |
97 | .algolia-autocomplete .algolia-docsearch-suggestion--title {
98 | display: block;
99 | padding: .25rem 1rem;
100 | margin-bottom: 0;
101 | font-size: 0.9em;
102 | font-weight: 400
103 | }
104 |
105 | .algolia-autocomplete .algolia-docsearch-suggestion--text {
106 | padding: 0 1rem .5rem;
107 | margin-top: -.25rem;
108 | font-size: 0.8em;
109 | font-weight: 400;
110 | line-height: 1.25
111 | }
112 |
113 | .algolia-autocomplete .algolia-docsearch-footer {
114 | width: 110px;
115 | height: 20px;
116 | z-index: 3;
117 | margin-top: 10.66667px;
118 | float: right;
119 | font-size: 0;
120 | line-height: 0;
121 | }
122 |
123 | .algolia-autocomplete .algolia-docsearch-footer--logo {
124 | background-image: url("data:image/svg+xml;utf8,");
125 | background-repeat: no-repeat;
126 | background-position: 50%;
127 | background-size: 100%;
128 | overflow: hidden;
129 | text-indent: -9000px;
130 | width: 100%;
131 | height: 100%;
132 | display: block;
133 | transform: translate(-8px);
134 | }
135 |
136 | .algolia-autocomplete .algolia-docsearch-suggestion--highlight {
137 | color: #FF8C00;
138 | background: rgba(232, 189, 54, 0.1)
139 | }
140 |
141 |
142 | .algolia-autocomplete .algolia-docsearch-suggestion--text .algolia-docsearch-suggestion--highlight {
143 | box-shadow: inset 0 -2px 0 0 rgba(105, 105, 105, .5)
144 | }
145 |
146 | .algolia-autocomplete .ds-suggestion.ds-cursor .algolia-docsearch-suggestion--content {
147 | background-color: rgba(192, 192, 192, .15)
148 | }
149 |
--------------------------------------------------------------------------------
/docs/docsearch.js:
--------------------------------------------------------------------------------
1 | $(function() {
2 |
3 | // register a handler to move the focus to the search bar
4 | // upon pressing shift + "/" (i.e. "?")
5 | $(document).on('keydown', function(e) {
6 | if (e.shiftKey && e.keyCode == 191) {
7 | e.preventDefault();
8 | $("#search-input").focus();
9 | }
10 | });
11 |
12 | $(document).ready(function() {
13 | // do keyword highlighting
14 | /* modified from https://jsfiddle.net/julmot/bL6bb5oo/ */
15 | var mark = function() {
16 |
17 | var referrer = document.URL ;
18 | var paramKey = "q" ;
19 |
20 | if (referrer.indexOf("?") !== -1) {
21 | var qs = referrer.substr(referrer.indexOf('?') + 1);
22 | var qs_noanchor = qs.split('#')[0];
23 | var qsa = qs_noanchor.split('&');
24 | var keyword = "";
25 |
26 | for (var i = 0; i < qsa.length; i++) {
27 | var currentParam = qsa[i].split('=');
28 |
29 | if (currentParam.length !== 2) {
30 | continue;
31 | }
32 |
33 | if (currentParam[0] == paramKey) {
34 | keyword = decodeURIComponent(currentParam[1].replace(/\+/g, "%20"));
35 | }
36 | }
37 |
38 | if (keyword !== "") {
39 | $(".contents").unmark({
40 | done: function() {
41 | $(".contents").mark(keyword);
42 | }
43 | });
44 | }
45 | }
46 | };
47 |
48 | mark();
49 | });
50 | });
51 |
52 | /* Search term highlighting ------------------------------*/
53 |
54 | function matchedWords(hit) {
55 | var words = [];
56 |
57 | var hierarchy = hit._highlightResult.hierarchy;
58 | // loop to fetch from lvl0, lvl1, etc.
59 | for (var idx in hierarchy) {
60 | words = words.concat(hierarchy[idx].matchedWords);
61 | }
62 |
63 | var content = hit._highlightResult.content;
64 | if (content) {
65 | words = words.concat(content.matchedWords);
66 | }
67 |
68 | // return unique words
69 | var words_uniq = [...new Set(words)];
70 | return words_uniq;
71 | }
72 |
73 | function updateHitURL(hit) {
74 |
75 | var words = matchedWords(hit);
76 | var url = "";
77 |
78 | if (hit.anchor) {
79 | url = hit.url_without_anchor + '?q=' + escape(words.join(" ")) + '#' + hit.anchor;
80 | } else {
81 | url = hit.url + '?q=' + escape(words.join(" "));
82 | }
83 |
84 | return url;
85 | }
86 |
--------------------------------------------------------------------------------
/docs/index.html:
--------------------------------------------------------------------------------
1 |
2 |
3 |
4 |
5 |
6 |
7 |
8 | Downloading YouTube Subtitle Transcription in a Tidy Tibble Data Frame • youtubecaption
9 |
10 |
11 |
12 |
13 |
14 |
15 |
16 |
20 |
21 |
22 |
23 |
78 |
79 |
80 |
81 |
82 |
83 |
84 |
85 |
87 |
88 |
89 |
90 |
91 | Motivation
92 | Although there exist some R packages tailored for YouTube API (e.g., ‘tuber’), downloading YouTube video subtitle (i.e., caption) in a tidy form has never been a low-hanging fruit. Using ‘youtube-transcript-api’ Python package under the hood, this R package provides users with a convenient way of parsing and converting a desired YouTube caption into a handy tibble data_frame object. Furthermore, users can easily save a desired YouTube caption data as a tidy Excel file without advanced programming background knowledge.
93 |
94 |
95 |
96 | Installation
97 |
98 |
99 | Python Dependencies
100 | youtubecaption requires Anaconda Python environment on your system Path.
101 | If you have not installed Conda environment on your system, please download and install Anaconda (Python 3.6 or later is recommended).
102 | For this package, I have employed youtube-transcript-api Python module into R using reticulate.
103 |
104 |
108 |
109 |
110 | Development Version
111 | You can install the latest development version as follows:
112 | if(!require(remotes)) {
113 | install.packages("remotes")
114 | }
115 |
116 | remotes::install_github("jooyoungseo/youtubecaption")
117 |
118 |
119 |
120 | Stable Version
121 | You can install the released version of youtubecaption from CRAN with:
122 | install.packages('youtubecaption')
123 |
124 |
125 |
126 |
127 | Usage
128 | Please use get_caption() function after loading youtubecaption package like below:
129 | library(youtubecaption)
130 |
131 | # Let's get the video caption out of Hadley Wickham's "You can't do data science in a GUI":
132 | url <- "https://www.youtube.com/watch?v=cpbtcsGE0OA"
133 | caption <- get_caption(url)
134 | caption
135 |
136 | #> # A tibble: 1,420 x 5
137 | #> segment_id text start duration vid
138 | #> <int> <chr> <dbl> <dbl> <chr>
139 | #> 1 1 thank you for coming to a meeting ~ 7.13 8.32 cpbtcsGE0~
140 | #> 2 2 in regards to data science GUI with 10.7 8.44 cpbtcsGE0~
141 | #> 3 3 happy with chief data scientist in~ 15.4 7.11 cpbtcsGE0~
142 | #> 4 4 studio as well as the member of th~ 19.1 7.23 cpbtcsGE0~
143 | #> 5 5 Foundation and an attempt professo~ 22.6 6 cpbtcsGE0~
144 | #> 6 6 Stanford and at the University of 26.4 6.48 cpbtcsGE0~
145 | #> 7 7 Auckland he builds both computatio~ 28.6 7.17 cpbtcsGE0~
146 | #> 8 8 and cognitive tools to make data s~ 32.8 7.5 cpbtcsGE0~
147 | #> 9 9 easier faster and more times his w~ 35.7 7.01 cpbtcsGE0~
148 | #> 10 10 includes various packages as well ~ 40.4 6.21 cpbtcsGE0~
149 | #> # ... with 1,410 more rows
150 |
151 | # Save the caption as an Excel file and open it right away:
152 | get_caption(url = url, savexl = TRUE, openxl = TRUE)
153 |
154 |
155 |
156 |
157 |
202 |
203 |
204 |
205 |
214 |
215 |
216 |
217 |
218 |
219 |
220 |
221 |
--------------------------------------------------------------------------------
/docs/link.svg:
--------------------------------------------------------------------------------
1 |
2 |
3 |
13 |
--------------------------------------------------------------------------------
/docs/news/index.html:
--------------------------------------------------------------------------------
1 |
2 |
3 |
4 |
5 |
6 |
7 |
8 |
9 | Changelog • youtubecaption
10 |
11 |
12 |
13 |
14 |
15 |
16 |
17 |
18 |
19 |
20 |
21 |
22 |
23 |
24 |
25 |
26 |
27 |
28 |
29 |
30 |
31 |
32 |
33 |
34 |
35 |
36 |
37 |
38 |
39 |
40 |
41 |
42 |
43 |
44 |
45 |
46 |
47 |
48 |
49 |
50 |
51 |
55 |
56 |
57 |
58 |
59 |
60 |
61 |
62 |
63 |
117 |
118 |
119 |
120 |
121 |
122 |
123 |
124 |
125 | Changelog
126 | Source: NEWS.md
127 |
128 |
129 |
130 |
131 | youtubecaption 1.0.0 2020-05-15
132 |
133 |
134 | - Added a new argument
language for get_caption() function (#1). You can now pass two-character language code; it is set to “en” (English) by default.
135 | - Cleaned up code indents for better readability.
136 |
137 |
138 |
146 |
147 |
148 | youtubecaption 0.1.2 2019-10-28
149 |
150 |
151 | -
152 |
CITATION file has been added.
153 |
154 |
155 |
156 |
157 | youtubecaption 0.1.1 2019-05-02
158 |
159 |
160 | - A critical bug that the third option
openxl of get_caption() does not work properly has been resolved.
161 |
162 |
163 |
171 |
172 |
173 |
178 |
179 |
180 |
181 |
182 |
192 |
193 |
194 |
195 |
196 |
197 |
198 |
199 |
200 |
201 |
--------------------------------------------------------------------------------
/docs/pkgdown.css:
--------------------------------------------------------------------------------
1 | /* Sticky footer */
2 |
3 | /**
4 | * Basic idea: https://philipwalton.github.io/solved-by-flexbox/demos/sticky-footer/
5 | * Details: https://github.com/philipwalton/solved-by-flexbox/blob/master/assets/css/components/site.css
6 | *
7 | * .Site -> body > .container
8 | * .Site-content -> body > .container .row
9 | * .footer -> footer
10 | *
11 | * Key idea seems to be to ensure that .container and __all its parents__
12 | * have height set to 100%
13 | *
14 | */
15 |
16 | html, body {
17 | height: 100%;
18 | }
19 |
20 | body {
21 | position: relative;
22 | }
23 |
24 | body > .container {
25 | display: flex;
26 | height: 100%;
27 | flex-direction: column;
28 | }
29 |
30 | body > .container .row {
31 | flex: 1 0 auto;
32 | }
33 |
34 | footer {
35 | margin-top: 45px;
36 | padding: 35px 0 36px;
37 | border-top: 1px solid #e5e5e5;
38 | color: #666;
39 | display: flex;
40 | flex-shrink: 0;
41 | }
42 | footer p {
43 | margin-bottom: 0;
44 | }
45 | footer div {
46 | flex: 1;
47 | }
48 | footer .pkgdown {
49 | text-align: right;
50 | }
51 | footer p {
52 | margin-bottom: 0;
53 | }
54 |
55 | img.icon {
56 | float: right;
57 | }
58 |
59 | img {
60 | max-width: 100%;
61 | }
62 |
63 | /* Fix bug in bootstrap (only seen in firefox) */
64 | summary {
65 | display: list-item;
66 | }
67 |
68 | /* Typographic tweaking ---------------------------------*/
69 |
70 | .contents .page-header {
71 | margin-top: calc(-60px + 1em);
72 | }
73 |
74 | dd {
75 | margin-left: 3em;
76 | }
77 |
78 | /* Section anchors ---------------------------------*/
79 |
80 | a.anchor {
81 | margin-left: -30px;
82 | display:inline-block;
83 | width: 30px;
84 | height: 30px;
85 | visibility: hidden;
86 |
87 | background-image: url(./link.svg);
88 | background-repeat: no-repeat;
89 | background-size: 20px 20px;
90 | background-position: center center;
91 | }
92 |
93 | .hasAnchor:hover a.anchor {
94 | visibility: visible;
95 | }
96 |
97 | @media (max-width: 767px) {
98 | .hasAnchor:hover a.anchor {
99 | visibility: hidden;
100 | }
101 | }
102 |
103 |
104 | /* Fixes for fixed navbar --------------------------*/
105 |
106 | .contents h1, .contents h2, .contents h3, .contents h4 {
107 | padding-top: 60px;
108 | margin-top: -40px;
109 | }
110 |
111 | /* Navbar submenu --------------------------*/
112 |
113 | .dropdown-submenu {
114 | position: relative;
115 | }
116 |
117 | .dropdown-submenu>.dropdown-menu {
118 | top: 0;
119 | left: 100%;
120 | margin-top: -6px;
121 | margin-left: -1px;
122 | border-radius: 0 6px 6px 6px;
123 | }
124 |
125 | .dropdown-submenu:hover>.dropdown-menu {
126 | display: block;
127 | }
128 |
129 | .dropdown-submenu>a:after {
130 | display: block;
131 | content: " ";
132 | float: right;
133 | width: 0;
134 | height: 0;
135 | border-color: transparent;
136 | border-style: solid;
137 | border-width: 5px 0 5px 5px;
138 | border-left-color: #cccccc;
139 | margin-top: 5px;
140 | margin-right: -10px;
141 | }
142 |
143 | .dropdown-submenu:hover>a:after {
144 | border-left-color: #ffffff;
145 | }
146 |
147 | .dropdown-submenu.pull-left {
148 | float: none;
149 | }
150 |
151 | .dropdown-submenu.pull-left>.dropdown-menu {
152 | left: -100%;
153 | margin-left: 10px;
154 | border-radius: 6px 0 6px 6px;
155 | }
156 |
157 | /* Sidebar --------------------------*/
158 |
159 | #pkgdown-sidebar {
160 | margin-top: 30px;
161 | position: -webkit-sticky;
162 | position: sticky;
163 | top: 70px;
164 | }
165 |
166 | #pkgdown-sidebar h2 {
167 | font-size: 1.5em;
168 | margin-top: 1em;
169 | }
170 |
171 | #pkgdown-sidebar h2:first-child {
172 | margin-top: 0;
173 | }
174 |
175 | #pkgdown-sidebar .list-unstyled li {
176 | margin-bottom: 0.5em;
177 | }
178 |
179 | /* bootstrap-toc tweaks ------------------------------------------------------*/
180 |
181 | /* All levels of nav */
182 |
183 | nav[data-toggle='toc'] .nav > li > a {
184 | padding: 4px 20px 4px 6px;
185 | font-size: 1.5rem;
186 | font-weight: 400;
187 | color: inherit;
188 | }
189 |
190 | nav[data-toggle='toc'] .nav > li > a:hover,
191 | nav[data-toggle='toc'] .nav > li > a:focus {
192 | padding-left: 5px;
193 | color: inherit;
194 | border-left: 1px solid #878787;
195 | }
196 |
197 | nav[data-toggle='toc'] .nav > .active > a,
198 | nav[data-toggle='toc'] .nav > .active:hover > a,
199 | nav[data-toggle='toc'] .nav > .active:focus > a {
200 | padding-left: 5px;
201 | font-size: 1.5rem;
202 | font-weight: 400;
203 | color: inherit;
204 | border-left: 2px solid #878787;
205 | }
206 |
207 | /* Nav: second level (shown on .active) */
208 |
209 | nav[data-toggle='toc'] .nav .nav {
210 | display: none; /* Hide by default, but at >768px, show it */
211 | padding-bottom: 10px;
212 | }
213 |
214 | nav[data-toggle='toc'] .nav .nav > li > a {
215 | padding-left: 16px;
216 | font-size: 1.35rem;
217 | }
218 |
219 | nav[data-toggle='toc'] .nav .nav > li > a:hover,
220 | nav[data-toggle='toc'] .nav .nav > li > a:focus {
221 | padding-left: 15px;
222 | }
223 |
224 | nav[data-toggle='toc'] .nav .nav > .active > a,
225 | nav[data-toggle='toc'] .nav .nav > .active:hover > a,
226 | nav[data-toggle='toc'] .nav .nav > .active:focus > a {
227 | padding-left: 15px;
228 | font-weight: 500;
229 | font-size: 1.35rem;
230 | }
231 |
232 | /* orcid ------------------------------------------------------------------- */
233 |
234 | .orcid {
235 | font-size: 16px;
236 | color: #A6CE39;
237 | /* margins are required by official ORCID trademark and display guidelines */
238 | margin-left:4px;
239 | margin-right:4px;
240 | vertical-align: middle;
241 | }
242 |
243 | /* Reference index & topics ----------------------------------------------- */
244 |
245 | .ref-index th {font-weight: normal;}
246 |
247 | .ref-index td {vertical-align: top;}
248 | .ref-index .icon {width: 40px;}
249 | .ref-index .alias {width: 40%;}
250 | .ref-index-icons .alias {width: calc(40% - 40px);}
251 | .ref-index .title {width: 60%;}
252 |
253 | .ref-arguments th {text-align: right; padding-right: 10px;}
254 | .ref-arguments th, .ref-arguments td {vertical-align: top;}
255 | .ref-arguments .name {width: 20%;}
256 | .ref-arguments .desc {width: 80%;}
257 |
258 | /* Nice scrolling for wide elements --------------------------------------- */
259 |
260 | table {
261 | display: block;
262 | overflow: auto;
263 | }
264 |
265 | /* Syntax highlighting ---------------------------------------------------- */
266 |
267 | pre {
268 | word-wrap: normal;
269 | word-break: normal;
270 | border: 1px solid #eee;
271 | }
272 |
273 | pre, code {
274 | background-color: #f8f8f8;
275 | color: #333;
276 | }
277 |
278 | pre code {
279 | overflow: auto;
280 | word-wrap: normal;
281 | white-space: pre;
282 | }
283 |
284 | pre .img {
285 | margin: 5px 0;
286 | }
287 |
288 | pre .img img {
289 | background-color: #fff;
290 | display: block;
291 | height: auto;
292 | }
293 |
294 | code a, pre a {
295 | color: #375f84;
296 | }
297 |
298 | a.sourceLine:hover {
299 | text-decoration: none;
300 | }
301 |
302 | .fl {color: #1514b5;}
303 | .fu {color: #000000;} /* function */
304 | .ch,.st {color: #036a07;} /* string */
305 | .kw {color: #264D66;} /* keyword */
306 | .co {color: #888888;} /* comment */
307 |
308 | .message { color: black; font-weight: bolder;}
309 | .error { color: orange; font-weight: bolder;}
310 | .warning { color: #6A0366; font-weight: bolder;}
311 |
312 | /* Clipboard --------------------------*/
313 |
314 | .hasCopyButton {
315 | position: relative;
316 | }
317 |
318 | .btn-copy-ex {
319 | position: absolute;
320 | right: 0;
321 | top: 0;
322 | visibility: hidden;
323 | }
324 |
325 | .hasCopyButton:hover button.btn-copy-ex {
326 | visibility: visible;
327 | }
328 |
329 | /* headroom.js ------------------------ */
330 |
331 | .headroom {
332 | will-change: transform;
333 | transition: transform 200ms linear;
334 | }
335 | .headroom--pinned {
336 | transform: translateY(0%);
337 | }
338 | .headroom--unpinned {
339 | transform: translateY(-100%);
340 | }
341 |
342 | /* mark.js ----------------------------*/
343 |
344 | mark {
345 | background-color: rgba(255, 255, 51, 0.5);
346 | border-bottom: 2px solid rgba(255, 153, 51, 0.3);
347 | padding: 1px;
348 | }
349 |
350 | /* vertical spacing after htmlwidgets */
351 | .html-widget {
352 | margin-bottom: 10px;
353 | }
354 |
355 | /* fontawesome ------------------------ */
356 |
357 | .fab {
358 | font-family: "Font Awesome 5 Brands" !important;
359 | }
360 |
361 | /* don't display links in code chunks when printing */
362 | /* source: https://stackoverflow.com/a/10781533 */
363 | @media print {
364 | code a:link:after, code a:visited:after {
365 | content: "";
366 | }
367 | }
368 |
--------------------------------------------------------------------------------
/docs/pkgdown.js:
--------------------------------------------------------------------------------
1 | /* http://gregfranko.com/blog/jquery-best-practices/ */
2 | (function($) {
3 | $(function() {
4 |
5 | $('.navbar-fixed-top').headroom();
6 |
7 | $('body').css('padding-top', $('.navbar').height() + 10);
8 | $(window).resize(function(){
9 | $('body').css('padding-top', $('.navbar').height() + 10);
10 | });
11 |
12 | $('[data-toggle="tooltip"]').tooltip();
13 |
14 | var cur_path = paths(location.pathname);
15 | var links = $("#navbar ul li a");
16 | var max_length = -1;
17 | var pos = -1;
18 | for (var i = 0; i < links.length; i++) {
19 | if (links[i].getAttribute("href") === "#")
20 | continue;
21 | // Ignore external links
22 | if (links[i].host !== location.host)
23 | continue;
24 |
25 | var nav_path = paths(links[i].pathname);
26 |
27 | var length = prefix_length(nav_path, cur_path);
28 | if (length > max_length) {
29 | max_length = length;
30 | pos = i;
31 | }
32 | }
33 |
34 | // Add class to parent
`).
76 | getTopLevel: function($scope) {
77 | for (var i = 1; i <= 6; i++) {
78 | var $headings = this.findOrFilter($scope, 'h' + i);
79 | if ($headings.length > 1) {
80 | return i;
81 | }
82 | }
83 |
84 | return 1;
85 | },
86 |
87 | // returns the elements for the top level, and the next below it
88 | getHeadings: function($scope, topLevel) {
89 | var topSelector = 'h' + topLevel;
90 |
91 | var secondaryLevel = topLevel + 1;
92 | var secondarySelector = 'h' + secondaryLevel;
93 |
94 | return this.findOrFilter($scope, topSelector + ',' + secondarySelector);
95 | },
96 |
97 | getNavLevel: function(el) {
98 | return parseInt(el.tagName.charAt(1), 10);
99 | },
100 |
101 | populateNav: function($topContext, topLevel, $headings) {
102 | var $context = $topContext;
103 | var $prevNav;
104 |
105 | var helpers = this;
106 | $headings.each(function(i, el) {
107 | var $newNav = helpers.generateNavItem(el);
108 | var navLevel = helpers.getNavLevel(el);
109 |
110 | // determine the proper $context
111 | if (navLevel === topLevel) {
112 | // use top level
113 | $context = $topContext;
114 | } else if ($prevNav && $context === $topContext) {
115 | // create a new level of the tree and switch to it
116 | $context = helpers.createChildNavList($prevNav);
117 | } // else use the current $context
118 |
119 | $context.append($newNav);
120 |
121 | $prevNav = $newNav;
122 | });
123 | },
124 |
125 | parseOps: function(arg) {
126 | var opts;
127 | if (arg.jquery) {
128 | opts = {
129 | $nav: arg
130 | };
131 | } else {
132 | opts = arg;
133 | }
134 | opts.$scope = opts.$scope || $(document.body);
135 | return opts;
136 | }
137 | },
138 |
139 | // accepts a jQuery object, or an options object
140 | init: function(opts) {
141 | opts = this.helpers.parseOps(opts);
142 |
143 | // ensure that the data attribute is in place for styling
144 | opts.$nav.attr('data-toggle', 'toc');
145 |
146 | var $topContext = this.helpers.createChildNavList(opts.$nav);
147 | var topLevel = this.helpers.getTopLevel(opts.$scope);
148 | var $headings = this.helpers.getHeadings(opts.$scope, topLevel);
149 | this.helpers.populateNav($topContext, topLevel, $headings);
150 | }
151 | };
152 |
153 | $(function() {
154 | $('nav[data-toggle="toc"]').each(function(i, el) {
155 | var $nav = $(el);
156 | Toc.init($nav);
157 | });
158 | });
159 | })();
160 |
--------------------------------------------------------------------------------
/docs/docsearch.css:
--------------------------------------------------------------------------------
1 | /* Docsearch -------------------------------------------------------------- */
2 | /*
3 | Source: https://github.com/algolia/docsearch/
4 | License: MIT
5 | */
6 |
7 | .algolia-autocomplete {
8 | display: block;
9 | -webkit-box-flex: 1;
10 | -ms-flex: 1;
11 | flex: 1
12 | }
13 |
14 | .algolia-autocomplete .ds-dropdown-menu {
15 | width: 100%;
16 | min-width: none;
17 | max-width: none;
18 | padding: .75rem 0;
19 | background-color: #fff;
20 | background-clip: padding-box;
21 | border: 1px solid rgba(0, 0, 0, .1);
22 | box-shadow: 0 .5rem 1rem rgba(0, 0, 0, .175);
23 | }
24 |
25 | @media (min-width:768px) {
26 | .algolia-autocomplete .ds-dropdown-menu {
27 | width: 175%
28 | }
29 | }
30 |
31 | .algolia-autocomplete .ds-dropdown-menu::before {
32 | display: none
33 | }
34 |
35 | .algolia-autocomplete .ds-dropdown-menu [class^=ds-dataset-] {
36 | padding: 0;
37 | background-color: rgb(255,255,255);
38 | border: 0;
39 | max-height: 80vh;
40 | }
41 |
42 | .algolia-autocomplete .ds-dropdown-menu .ds-suggestions {
43 | margin-top: 0
44 | }
45 |
46 | .algolia-autocomplete .algolia-docsearch-suggestion {
47 | padding: 0;
48 | overflow: visible
49 | }
50 |
51 | .algolia-autocomplete .algolia-docsearch-suggestion--category-header {
52 | padding: .125rem 1rem;
53 | margin-top: 0;
54 | font-size: 1.3em;
55 | font-weight: 500;
56 | color: #00008B;
57 | border-bottom: 0
58 | }
59 |
60 | .algolia-autocomplete .algolia-docsearch-suggestion--wrapper {
61 | float: none;
62 | padding-top: 0
63 | }
64 |
65 | .algolia-autocomplete .algolia-docsearch-suggestion--subcategory-column {
66 | float: none;
67 | width: auto;
68 | padding: 0;
69 | text-align: left
70 | }
71 |
72 | .algolia-autocomplete .algolia-docsearch-suggestion--content {
73 | float: none;
74 | width: auto;
75 | padding: 0
76 | }
77 |
78 | .algolia-autocomplete .algolia-docsearch-suggestion--content::before {
79 | display: none
80 | }
81 |
82 | .algolia-autocomplete .ds-suggestion:not(:first-child) .algolia-docsearch-suggestion--category-header {
83 | padding-top: .75rem;
84 | margin-top: .75rem;
85 | border-top: 1px solid rgba(0, 0, 0, .1)
86 | }
87 |
88 | .algolia-autocomplete .ds-suggestion .algolia-docsearch-suggestion--subcategory-column {
89 | display: block;
90 | padding: .1rem 1rem;
91 | margin-bottom: 0.1;
92 | font-size: 1.0em;
93 | font-weight: 400
94 | /* display: none */
95 | }
96 |
97 | .algolia-autocomplete .algolia-docsearch-suggestion--title {
98 | display: block;
99 | padding: .25rem 1rem;
100 | margin-bottom: 0;
101 | font-size: 0.9em;
102 | font-weight: 400
103 | }
104 |
105 | .algolia-autocomplete .algolia-docsearch-suggestion--text {
106 | padding: 0 1rem .5rem;
107 | margin-top: -.25rem;
108 | font-size: 0.8em;
109 | font-weight: 400;
110 | line-height: 1.25
111 | }
112 |
113 | .algolia-autocomplete .algolia-docsearch-footer {
114 | width: 110px;
115 | height: 20px;
116 | z-index: 3;
117 | margin-top: 10.66667px;
118 | float: right;
119 | font-size: 0;
120 | line-height: 0;
121 | }
122 |
123 | .algolia-autocomplete .algolia-docsearch-footer--logo {
124 | background-image: url("data:image/svg+xml;utf8,");
125 | background-repeat: no-repeat;
126 | background-position: 50%;
127 | background-size: 100%;
128 | overflow: hidden;
129 | text-indent: -9000px;
130 | width: 100%;
131 | height: 100%;
132 | display: block;
133 | transform: translate(-8px);
134 | }
135 |
136 | .algolia-autocomplete .algolia-docsearch-suggestion--highlight {
137 | color: #FF8C00;
138 | background: rgba(232, 189, 54, 0.1)
139 | }
140 |
141 |
142 | .algolia-autocomplete .algolia-docsearch-suggestion--text .algolia-docsearch-suggestion--highlight {
143 | box-shadow: inset 0 -2px 0 0 rgba(105, 105, 105, .5)
144 | }
145 |
146 | .algolia-autocomplete .ds-suggestion.ds-cursor .algolia-docsearch-suggestion--content {
147 | background-color: rgba(192, 192, 192, .15)
148 | }
149 |
--------------------------------------------------------------------------------
/docs/docsearch.js:
--------------------------------------------------------------------------------
1 | $(function() {
2 |
3 | // register a handler to move the focus to the search bar
4 | // upon pressing shift + "/" (i.e. "?")
5 | $(document).on('keydown', function(e) {
6 | if (e.shiftKey && e.keyCode == 191) {
7 | e.preventDefault();
8 | $("#search-input").focus();
9 | }
10 | });
11 |
12 | $(document).ready(function() {
13 | // do keyword highlighting
14 | /* modified from https://jsfiddle.net/julmot/bL6bb5oo/ */
15 | var mark = function() {
16 |
17 | var referrer = document.URL ;
18 | var paramKey = "q" ;
19 |
20 | if (referrer.indexOf("?") !== -1) {
21 | var qs = referrer.substr(referrer.indexOf('?') + 1);
22 | var qs_noanchor = qs.split('#')[0];
23 | var qsa = qs_noanchor.split('&');
24 | var keyword = "";
25 |
26 | for (var i = 0; i < qsa.length; i++) {
27 | var currentParam = qsa[i].split('=');
28 |
29 | if (currentParam.length !== 2) {
30 | continue;
31 | }
32 |
33 | if (currentParam[0] == paramKey) {
34 | keyword = decodeURIComponent(currentParam[1].replace(/\+/g, "%20"));
35 | }
36 | }
37 |
38 | if (keyword !== "") {
39 | $(".contents").unmark({
40 | done: function() {
41 | $(".contents").mark(keyword);
42 | }
43 | });
44 | }
45 | }
46 | };
47 |
48 | mark();
49 | });
50 | });
51 |
52 | /* Search term highlighting ------------------------------*/
53 |
54 | function matchedWords(hit) {
55 | var words = [];
56 |
57 | var hierarchy = hit._highlightResult.hierarchy;
58 | // loop to fetch from lvl0, lvl1, etc.
59 | for (var idx in hierarchy) {
60 | words = words.concat(hierarchy[idx].matchedWords);
61 | }
62 |
63 | var content = hit._highlightResult.content;
64 | if (content) {
65 | words = words.concat(content.matchedWords);
66 | }
67 |
68 | // return unique words
69 | var words_uniq = [...new Set(words)];
70 | return words_uniq;
71 | }
72 |
73 | function updateHitURL(hit) {
74 |
75 | var words = matchedWords(hit);
76 | var url = "";
77 |
78 | if (hit.anchor) {
79 | url = hit.url_without_anchor + '?q=' + escape(words.join(" ")) + '#' + hit.anchor;
80 | } else {
81 | url = hit.url + '?q=' + escape(words.join(" "));
82 | }
83 |
84 | return url;
85 | }
86 |
--------------------------------------------------------------------------------
/docs/index.html:
--------------------------------------------------------------------------------
1 |
2 |
3 |
4 |
5 |
6 |
7 |
8 | Downloading YouTube Subtitle Transcription in a Tidy Tibble Data Frame • youtubecaption
9 |
10 |
11 |
12 |
13 |
14 |
15 |
16 |
20 |
21 |
22 |
23 |
78 |
79 |
80 |
81 |
82 |
83 |
84 |
85 |
87 |
88 |
89 |
90 |
91 | Motivation
92 | Although there exist some R packages tailored for YouTube API (e.g., ‘tuber’), downloading YouTube video subtitle (i.e., caption) in a tidy form has never been a low-hanging fruit. Using ‘youtube-transcript-api’ Python package under the hood, this R package provides users with a convenient way of parsing and converting a desired YouTube caption into a handy tibble data_frame object. Furthermore, users can easily save a desired YouTube caption data as a tidy Excel file without advanced programming background knowledge.
93 |
94 |
95 |
96 | Installation
97 |
98 |
99 | Python Dependencies
100 | youtubecaption requires Anaconda Python environment on your system Path.
101 | If you have not installed Conda environment on your system, please download and install Anaconda (Python 3.6 or later is recommended).
102 | For this package, I have employed youtube-transcript-api Python module into R using reticulate.
103 |
104 |
108 |
109 |
110 | Development Version
111 | You can install the latest development version as follows:
112 | if(!require(remotes)) {
113 | install.packages("remotes")
114 | }
115 |
116 | remotes::install_github("jooyoungseo/youtubecaption")
117 |
118 |
119 |
120 | Stable Version
121 | You can install the released version of youtubecaption from CRAN with:
122 | install.packages('youtubecaption')
123 |
124 |
125 |
126 |
127 | Usage
128 | Please use get_caption() function after loading youtubecaption package like below:
129 | library(youtubecaption)
130 |
131 | # Let's get the video caption out of Hadley Wickham's "You can't do data science in a GUI":
132 | url <- "https://www.youtube.com/watch?v=cpbtcsGE0OA"
133 | caption <- get_caption(url)
134 | caption
135 |
136 | #> # A tibble: 1,420 x 5
137 | #> segment_id text start duration vid
138 | #> <int> <chr> <dbl> <dbl> <chr>
139 | #> 1 1 thank you for coming to a meeting ~ 7.13 8.32 cpbtcsGE0~
140 | #> 2 2 in regards to data science GUI with 10.7 8.44 cpbtcsGE0~
141 | #> 3 3 happy with chief data scientist in~ 15.4 7.11 cpbtcsGE0~
142 | #> 4 4 studio as well as the member of th~ 19.1 7.23 cpbtcsGE0~
143 | #> 5 5 Foundation and an attempt professo~ 22.6 6 cpbtcsGE0~
144 | #> 6 6 Stanford and at the University of 26.4 6.48 cpbtcsGE0~
145 | #> 7 7 Auckland he builds both computatio~ 28.6 7.17 cpbtcsGE0~
146 | #> 8 8 and cognitive tools to make data s~ 32.8 7.5 cpbtcsGE0~
147 | #> 9 9 easier faster and more times his w~ 35.7 7.01 cpbtcsGE0~
148 | #> 10 10 includes various packages as well ~ 40.4 6.21 cpbtcsGE0~
149 | #> # ... with 1,410 more rows
150 |
151 | # Save the caption as an Excel file and open it right away:
152 | get_caption(url = url, savexl = TRUE, openxl = TRUE)
153 |
154 |
155 |
156 |
157 |
202 |
203 |
204 |
205 |
214 |
215 |
216 |
217 |
218 |
219 |
220 |
221 |
--------------------------------------------------------------------------------
/docs/link.svg:
--------------------------------------------------------------------------------
1 |
2 |
3 |
13 |
--------------------------------------------------------------------------------
/docs/news/index.html:
--------------------------------------------------------------------------------
1 |
2 |
3 |
4 |
5 |
6 |
7 |
8 |
9 | Changelog • youtubecaption
10 |
11 |
12 |
13 |
14 |
15 |
16 |
17 |
18 |
19 |
20 |
21 |
22 |
23 |
24 |
25 |
26 |
27 |
28 |
29 |
30 |
31 |
32 |
33 |
34 |
35 |
36 |
37 |
38 |
39 |
40 |
41 |
42 |
43 |
44 |
45 |
46 |
47 |
48 |
49 |
50 |
51 |
55 |
56 |
57 |
58 |
59 |
60 |
61 |
62 |
63 |
117 |
118 |
119 |
120 |
121 |
122 |
123 |
124 |
125 | Changelog
126 | Source: NEWS.md
127 |
128 |
129 |
130 |
131 | youtubecaption 1.0.0 2020-05-15
132 |
133 |
134 | - Added a new argument
language for get_caption() function (#1). You can now pass two-character language code; it is set to “en” (English) by default.
135 | - Cleaned up code indents for better readability.
136 |
137 |
138 |
146 |
147 |
148 | youtubecaption 0.1.2 2019-10-28
149 |
150 |
151 | -
152 |
CITATION file has been added.
153 |
154 |
155 |
156 |
157 | youtubecaption 0.1.1 2019-05-02
158 |
159 |
160 | - A critical bug that the third option
openxl of get_caption() does not work properly has been resolved.
161 |
162 |
163 |
171 |
172 |
173 |
178 |
179 |
180 |
181 |
182 |
192 |
193 |
194 |
195 |
196 |
197 |
198 |
199 |
200 |
201 |
--------------------------------------------------------------------------------
/docs/pkgdown.css:
--------------------------------------------------------------------------------
1 | /* Sticky footer */
2 |
3 | /**
4 | * Basic idea: https://philipwalton.github.io/solved-by-flexbox/demos/sticky-footer/
5 | * Details: https://github.com/philipwalton/solved-by-flexbox/blob/master/assets/css/components/site.css
6 | *
7 | * .Site -> body > .container
8 | * .Site-content -> body > .container .row
9 | * .footer -> footer
10 | *
11 | * Key idea seems to be to ensure that .container and __all its parents__
12 | * have height set to 100%
13 | *
14 | */
15 |
16 | html, body {
17 | height: 100%;
18 | }
19 |
20 | body {
21 | position: relative;
22 | }
23 |
24 | body > .container {
25 | display: flex;
26 | height: 100%;
27 | flex-direction: column;
28 | }
29 |
30 | body > .container .row {
31 | flex: 1 0 auto;
32 | }
33 |
34 | footer {
35 | margin-top: 45px;
36 | padding: 35px 0 36px;
37 | border-top: 1px solid #e5e5e5;
38 | color: #666;
39 | display: flex;
40 | flex-shrink: 0;
41 | }
42 | footer p {
43 | margin-bottom: 0;
44 | }
45 | footer div {
46 | flex: 1;
47 | }
48 | footer .pkgdown {
49 | text-align: right;
50 | }
51 | footer p {
52 | margin-bottom: 0;
53 | }
54 |
55 | img.icon {
56 | float: right;
57 | }
58 |
59 | img {
60 | max-width: 100%;
61 | }
62 |
63 | /* Fix bug in bootstrap (only seen in firefox) */
64 | summary {
65 | display: list-item;
66 | }
67 |
68 | /* Typographic tweaking ---------------------------------*/
69 |
70 | .contents .page-header {
71 | margin-top: calc(-60px + 1em);
72 | }
73 |
74 | dd {
75 | margin-left: 3em;
76 | }
77 |
78 | /* Section anchors ---------------------------------*/
79 |
80 | a.anchor {
81 | margin-left: -30px;
82 | display:inline-block;
83 | width: 30px;
84 | height: 30px;
85 | visibility: hidden;
86 |
87 | background-image: url(./link.svg);
88 | background-repeat: no-repeat;
89 | background-size: 20px 20px;
90 | background-position: center center;
91 | }
92 |
93 | .hasAnchor:hover a.anchor {
94 | visibility: visible;
95 | }
96 |
97 | @media (max-width: 767px) {
98 | .hasAnchor:hover a.anchor {
99 | visibility: hidden;
100 | }
101 | }
102 |
103 |
104 | /* Fixes for fixed navbar --------------------------*/
105 |
106 | .contents h1, .contents h2, .contents h3, .contents h4 {
107 | padding-top: 60px;
108 | margin-top: -40px;
109 | }
110 |
111 | /* Navbar submenu --------------------------*/
112 |
113 | .dropdown-submenu {
114 | position: relative;
115 | }
116 |
117 | .dropdown-submenu>.dropdown-menu {
118 | top: 0;
119 | left: 100%;
120 | margin-top: -6px;
121 | margin-left: -1px;
122 | border-radius: 0 6px 6px 6px;
123 | }
124 |
125 | .dropdown-submenu:hover>.dropdown-menu {
126 | display: block;
127 | }
128 |
129 | .dropdown-submenu>a:after {
130 | display: block;
131 | content: " ";
132 | float: right;
133 | width: 0;
134 | height: 0;
135 | border-color: transparent;
136 | border-style: solid;
137 | border-width: 5px 0 5px 5px;
138 | border-left-color: #cccccc;
139 | margin-top: 5px;
140 | margin-right: -10px;
141 | }
142 |
143 | .dropdown-submenu:hover>a:after {
144 | border-left-color: #ffffff;
145 | }
146 |
147 | .dropdown-submenu.pull-left {
148 | float: none;
149 | }
150 |
151 | .dropdown-submenu.pull-left>.dropdown-menu {
152 | left: -100%;
153 | margin-left: 10px;
154 | border-radius: 6px 0 6px 6px;
155 | }
156 |
157 | /* Sidebar --------------------------*/
158 |
159 | #pkgdown-sidebar {
160 | margin-top: 30px;
161 | position: -webkit-sticky;
162 | position: sticky;
163 | top: 70px;
164 | }
165 |
166 | #pkgdown-sidebar h2 {
167 | font-size: 1.5em;
168 | margin-top: 1em;
169 | }
170 |
171 | #pkgdown-sidebar h2:first-child {
172 | margin-top: 0;
173 | }
174 |
175 | #pkgdown-sidebar .list-unstyled li {
176 | margin-bottom: 0.5em;
177 | }
178 |
179 | /* bootstrap-toc tweaks ------------------------------------------------------*/
180 |
181 | /* All levels of nav */
182 |
183 | nav[data-toggle='toc'] .nav > li > a {
184 | padding: 4px 20px 4px 6px;
185 | font-size: 1.5rem;
186 | font-weight: 400;
187 | color: inherit;
188 | }
189 |
190 | nav[data-toggle='toc'] .nav > li > a:hover,
191 | nav[data-toggle='toc'] .nav > li > a:focus {
192 | padding-left: 5px;
193 | color: inherit;
194 | border-left: 1px solid #878787;
195 | }
196 |
197 | nav[data-toggle='toc'] .nav > .active > a,
198 | nav[data-toggle='toc'] .nav > .active:hover > a,
199 | nav[data-toggle='toc'] .nav > .active:focus > a {
200 | padding-left: 5px;
201 | font-size: 1.5rem;
202 | font-weight: 400;
203 | color: inherit;
204 | border-left: 2px solid #878787;
205 | }
206 |
207 | /* Nav: second level (shown on .active) */
208 |
209 | nav[data-toggle='toc'] .nav .nav {
210 | display: none; /* Hide by default, but at >768px, show it */
211 | padding-bottom: 10px;
212 | }
213 |
214 | nav[data-toggle='toc'] .nav .nav > li > a {
215 | padding-left: 16px;
216 | font-size: 1.35rem;
217 | }
218 |
219 | nav[data-toggle='toc'] .nav .nav > li > a:hover,
220 | nav[data-toggle='toc'] .nav .nav > li > a:focus {
221 | padding-left: 15px;
222 | }
223 |
224 | nav[data-toggle='toc'] .nav .nav > .active > a,
225 | nav[data-toggle='toc'] .nav .nav > .active:hover > a,
226 | nav[data-toggle='toc'] .nav .nav > .active:focus > a {
227 | padding-left: 15px;
228 | font-weight: 500;
229 | font-size: 1.35rem;
230 | }
231 |
232 | /* orcid ------------------------------------------------------------------- */
233 |
234 | .orcid {
235 | font-size: 16px;
236 | color: #A6CE39;
237 | /* margins are required by official ORCID trademark and display guidelines */
238 | margin-left:4px;
239 | margin-right:4px;
240 | vertical-align: middle;
241 | }
242 |
243 | /* Reference index & topics ----------------------------------------------- */
244 |
245 | .ref-index th {font-weight: normal;}
246 |
247 | .ref-index td {vertical-align: top;}
248 | .ref-index .icon {width: 40px;}
249 | .ref-index .alias {width: 40%;}
250 | .ref-index-icons .alias {width: calc(40% - 40px);}
251 | .ref-index .title {width: 60%;}
252 |
253 | .ref-arguments th {text-align: right; padding-right: 10px;}
254 | .ref-arguments th, .ref-arguments td {vertical-align: top;}
255 | .ref-arguments .name {width: 20%;}
256 | .ref-arguments .desc {width: 80%;}
257 |
258 | /* Nice scrolling for wide elements --------------------------------------- */
259 |
260 | table {
261 | display: block;
262 | overflow: auto;
263 | }
264 |
265 | /* Syntax highlighting ---------------------------------------------------- */
266 |
267 | pre {
268 | word-wrap: normal;
269 | word-break: normal;
270 | border: 1px solid #eee;
271 | }
272 |
273 | pre, code {
274 | background-color: #f8f8f8;
275 | color: #333;
276 | }
277 |
278 | pre code {
279 | overflow: auto;
280 | word-wrap: normal;
281 | white-space: pre;
282 | }
283 |
284 | pre .img {
285 | margin: 5px 0;
286 | }
287 |
288 | pre .img img {
289 | background-color: #fff;
290 | display: block;
291 | height: auto;
292 | }
293 |
294 | code a, pre a {
295 | color: #375f84;
296 | }
297 |
298 | a.sourceLine:hover {
299 | text-decoration: none;
300 | }
301 |
302 | .fl {color: #1514b5;}
303 | .fu {color: #000000;} /* function */
304 | .ch,.st {color: #036a07;} /* string */
305 | .kw {color: #264D66;} /* keyword */
306 | .co {color: #888888;} /* comment */
307 |
308 | .message { color: black; font-weight: bolder;}
309 | .error { color: orange; font-weight: bolder;}
310 | .warning { color: #6A0366; font-weight: bolder;}
311 |
312 | /* Clipboard --------------------------*/
313 |
314 | .hasCopyButton {
315 | position: relative;
316 | }
317 |
318 | .btn-copy-ex {
319 | position: absolute;
320 | right: 0;
321 | top: 0;
322 | visibility: hidden;
323 | }
324 |
325 | .hasCopyButton:hover button.btn-copy-ex {
326 | visibility: visible;
327 | }
328 |
329 | /* headroom.js ------------------------ */
330 |
331 | .headroom {
332 | will-change: transform;
333 | transition: transform 200ms linear;
334 | }
335 | .headroom--pinned {
336 | transform: translateY(0%);
337 | }
338 | .headroom--unpinned {
339 | transform: translateY(-100%);
340 | }
341 |
342 | /* mark.js ----------------------------*/
343 |
344 | mark {
345 | background-color: rgba(255, 255, 51, 0.5);
346 | border-bottom: 2px solid rgba(255, 153, 51, 0.3);
347 | padding: 1px;
348 | }
349 |
350 | /* vertical spacing after htmlwidgets */
351 | .html-widget {
352 | margin-bottom: 10px;
353 | }
354 |
355 | /* fontawesome ------------------------ */
356 |
357 | .fab {
358 | font-family: "Font Awesome 5 Brands" !important;
359 | }
360 |
361 | /* don't display links in code chunks when printing */
362 | /* source: https://stackoverflow.com/a/10781533 */
363 | @media print {
364 | code a:link:after, code a:visited:after {
365 | content: "";
366 | }
367 | }
368 |
--------------------------------------------------------------------------------
/docs/pkgdown.js:
--------------------------------------------------------------------------------
1 | /* http://gregfranko.com/blog/jquery-best-practices/ */
2 | (function($) {
3 | $(function() {
4 |
5 | $('.navbar-fixed-top').headroom();
6 |
7 | $('body').css('padding-top', $('.navbar').height() + 10);
8 | $(window).resize(function(){
9 | $('body').css('padding-top', $('.navbar').height() + 10);
10 | });
11 |
12 | $('[data-toggle="tooltip"]').tooltip();
13 |
14 | var cur_path = paths(location.pathname);
15 | var links = $("#navbar ul li a");
16 | var max_length = -1;
17 | var pos = -1;
18 | for (var i = 0; i < links.length; i++) {
19 | if (links[i].getAttribute("href") === "#")
20 | continue;
21 | // Ignore external links
22 | if (links[i].host !== location.host)
23 | continue;
24 |
25 | var nav_path = paths(links[i].pathname);
26 |
27 | var length = prefix_length(nav_path, cur_path);
28 | if (length > max_length) {
29 | max_length = length;
30 | pos = i;
31 | }
32 | }
33 |
34 | // Add class to parent
83 |
203 |
204 |
205 |
214 |
84 |
156 |
157 |
202 |
85 |
87 |
88 |
89 |
155 |
90 |
94 | 91 | Motivation
92 |Although there exist some R packages tailored for YouTube API (e.g., ‘tuber’), downloading YouTube video subtitle (i.e., caption) in a tidy form has never been a low-hanging fruit. Using ‘youtube-transcript-api’ Python package under the hood, this R package provides users with a convenient way of parsing and converting a desired YouTube caption into a handy tibble data_frame object. Furthermore, users can easily save a desired YouTube caption data as a tidy Excel file without advanced programming background knowledge.
93 |
95 |
125 | 96 | Installation
97 |
98 |
104 |
108 | 99 | Python Dependencies
100 |youtubecaption requires Anaconda Python environment on your system Path.
If you have not installed Conda environment on your system, please download and install Anaconda (Python 3.6 or later is recommended).
102 |For this package, I have employed youtube-transcript-api Python module into R using reticulate.
103 |
109 |
117 |
118 | 110 | Development Version
111 |You can install the latest development version as follows:
112 |if(!require(remotes)) { 113 | install.packages("remotes") 114 | } 115 | 116 | remotes::install_github("jooyoungseo/youtubecaption")
119 |
123 |
124 | 120 | Stable Version
121 |You can install the released version of youtubecaption from CRAN with:
122 |install.packages('youtubecaption')
126 |
153 |
154 | 127 | Usage
128 |Please use get_caption() function after loading youtubecaption package like below:
library(youtubecaption) 130 | 131 | # Let's get the video caption out of Hadley Wickham's "You can't do data science in a GUI": 132 | url <- "https://www.youtube.com/watch?v=cpbtcsGE0OA" 133 | caption <- get_caption(url) 134 | caption 135 | 136 | #> # A tibble: 1,420 x 5 137 | #> segment_id text start duration vid 138 | #> <int> <chr> <dbl> <dbl> <chr> 139 | #> 1 1 thank you for coming to a meeting ~ 7.13 8.32 cpbtcsGE0~ 140 | #> 2 2 in regards to data science GUI with 10.7 8.44 cpbtcsGE0~ 141 | #> 3 3 happy with chief data scientist in~ 15.4 7.11 cpbtcsGE0~ 142 | #> 4 4 studio as well as the member of th~ 19.1 7.23 cpbtcsGE0~ 143 | #> 5 5 Foundation and an attempt professo~ 22.6 6 cpbtcsGE0~ 144 | #> 6 6 Stanford and at the University of 26.4 6.48 cpbtcsGE0~ 145 | #> 7 7 Auckland he builds both computatio~ 28.6 7.17 cpbtcsGE0~ 146 | #> 8 8 and cognitive tools to make data s~ 32.8 7.5 cpbtcsGE0~ 147 | #> 9 9 easier faster and more times his w~ 35.7 7.01 cpbtcsGE0~ 148 | #> 10 10 includes various packages as well ~ 40.4 6.21 cpbtcsGE0~ 149 | #> # ... with 1,410 more rows 150 | 151 | # Save the caption as an Excel file and open it right away: 152 | get_caption(url = url, savexl = TRUE, openxl = TRUE)
123 |
180 |
181 |
182 |
192 |
124 |
172 |
173 |
178 |
179 |
125 |
128 |
129 | Changelog
126 | Source:NEWS.md
127 |
130 |
138 |
146 | 131 | youtubecaption 1.0.0 2020-05-15 132 |
133 |-
134 |
- Added a new argument
languageforget_caption()function (#1). You can now pass two-character language code; it is set to “en” (English) by default.
135 | - Cleaned up code indents for better readability. 136 |
147 |
155 | 148 | youtubecaption 0.1.2 2019-10-28 149 |
150 |-
151 |
-
152 |
CITATIONfile has been added.
153 |
156 |
163 |
171 | 157 | youtubecaption 0.1.1 2019-05-02 158 |
159 |-
160 |
- A critical bug that the third option
openxlofget_caption()does not work properly has been resolved.
161 |
63 |
64 |
118 |
119 |
120 |
121 |
122 |
123 |
236 |
237 |
238 |
239 |
240 |
241 |
242 |
243 |
244 |
--------------------------------------------------------------------------------
/docs/reference/index.html:
--------------------------------------------------------------------------------
1 |
2 |
3 |
4 |
5 |
6 |
7 |
8 |
9 |
124 |
223 |
224 |
225 |
235 |
125 |
145 |
167 |
168 |
217 |
222 |
126 |
129 |
130 |
131 | Obtaining YouTube video caption/subtitle in a tidy tibble form.
127 | Source:R/get_caption.R
128 | get_caption.Rd
132 |
134 |
135 | Use this function for downloading a desired YouTube video caption in a tidy tibble data_frame form and save it as an Excel file in your current working directory.
133 |get_caption( 136 | url = NULL, 137 | language = "en", 138 | savexl = FALSE, 139 | openxl = FALSE, 140 | path = getwd() 141 | )142 | 143 |
Arguments
144 || url | 148 |A string value for a single YouTube video link URL. A typical form should start with "https://www.youtube.com/watch?v=" followed by a unique video ID. |
149 |
|---|---|
| language | 152 |two-character language code for the video URL. Set to "en" (English) by default. You can change this to fit with your needs (e.g., "ko" for Korean, "de" for German, etc.). |
153 |
| savexl | 156 |A logical value for determining whether or not to save the obtained tidy YouTube caption data as an Excel file. The default is FALSE which does not save it as a file. If set to TRUE, a file named "YouTube_caption_ |
157 |
| openxl | 160 |A logical value for determining whether or not to open, if any, the saved YouTube_caption Excel file in your working directory. The default is FALSE. TRUE works only when the preceding argument (i.e., savexl) is set to TRUE. |
161 |
| path | 164 |A character vector of full path names; the default corresponds to the working directory, getwd. Tilde expansion (see path.expand) is performed. Missing values will be ignored. |
165 |
Value
169 | 170 |tibble (advanced data.frame) object for a YouTube video caption will be returned.
171 |Details
172 | 173 |get_caption
174 |See example below.
175 |References
176 | 177 |https://pypi.org/project/youtube-transcript-api/
178 | 179 |Examples
180 |216 |# \donttest{ 181 | library(youtubecaption) 182 | # Let's get the video caption out of Hadley Wickham's "You can't do data science in a GUI": 183 | url <- "https://www.youtube.com/watch?v=cpbtcsGE0OA" 184 | caption <- get_caption(url)#> Warning: path[1]="C:\Anaconda3\envs\bookworm/python.exe": The system cannot find the file specified#> Warning: path[1]="C:\Anaconda3\envs\bookworm/python.exe": The system cannot find the file specifiedcaption#> # A tibble: 1,420 x 5 185 | #> segment_id text start duration vid 186 | #> <int> <chr> <dbl> <dbl> <chr> 187 | #> 1 1 thank you for coming to a meeting today 7.13 8.32 cpbtcsGE0~ 188 | #> 2 2 in regards to data science GUI with 10.7 8.44 cpbtcsGE0~ 189 | #> 3 3 happy with chief data scientist in our 15.4 7.11 cpbtcsGE0~ 190 | #> 4 4 studio as well as the member of the our 19.1 7.23 cpbtcsGE0~ 191 | #> 5 5 Foundation and an attempt professor at 22.6 6 cpbtcsGE0~ 192 | #> 6 6 Stanford and at the University of 26.4 6.48 cpbtcsGE0~ 193 | #> 7 7 Auckland he builds both computational 28.6 7.17 cpbtcsGE0~ 194 | #> 8 8 and cognitive tools to make data science 32.8 7.5 cpbtcsGE0~ 195 | #> 9 9 easier faster and more times his work 35.7 7.01 cpbtcsGE0~ 196 | #> 10 10 includes various packages as well as 40.4 6.21 cpbtcsGE0~ 197 | #> # ... with 1,410 more rows198 | # Save the caption as an Excel file and open it right it away 199 | ## Changing path to temp for the demonstration purpose only: 200 | get_caption(url = url, savexl = TRUE, openxl = TRUE, path = tempdir())#> Warning: path[1]="C:\Anaconda3\envs\bookworm/python.exe": The system cannot find the file specified#> Warning: path[1]="C:\Anaconda3\envs\bookworm/python.exe": The system cannot find the file specified#> # A tibble: 1,420 x 5 201 | #> segment_id text start duration vid 202 | #> <int> <chr> <dbl> <dbl> <chr> 203 | #> 1 1 thank you for coming to a meeting today 7.13 8.32 cpbtcsGE0~ 204 | #> 2 2 in regards to data science GUI with 10.7 8.44 cpbtcsGE0~ 205 | #> 3 3 happy with chief data scientist in our 15.4 7.11 cpbtcsGE0~ 206 | #> 4 4 studio as well as the member of the our 19.1 7.23 cpbtcsGE0~ 207 | #> 5 5 Foundation and an attempt professor at 22.6 6 cpbtcsGE0~ 208 | #> 6 6 Stanford and at the University of 26.4 6.48 cpbtcsGE0~ 209 | #> 7 7 Auckland he builds both computational 28.6 7.17 cpbtcsGE0~ 210 | #> 8 8 and cognitive tools to make data science 32.8 7.5 cpbtcsGE0~ 211 | #> 9 9 easier faster and more times his work 35.7 7.01 cpbtcsGE0~ 212 | #> 10 10 includes various packages as well as 40.4 6.21 cpbtcsGE0~ 213 | #> # ... with 1,410 more rows# } 214 | 215 |
62 |
63 |
117 |
118 |
119 |
120 |
121 |
122 |
178 |
179 |
180 |
181 |
182 |
183 |
184 |
185 |
186 |
--------------------------------------------------------------------------------
/docs/reference/pipe.html:
--------------------------------------------------------------------------------
1 |
2 |
3 |
4 |
5 |
6 |
7 |
8 |
9 |
123 |
158 |
159 |
164 |
165 |
166 |
167 |
177 |
63 |
64 |
118 |
119 |
120 |
121 |
122 |
123 |
159 |
160 |
161 |
162 |
163 |
164 |
165 |
166 |
167 |
--------------------------------------------------------------------------------
/docs/reference/youtubecaption-package.html:
--------------------------------------------------------------------------------
1 |
2 |
3 |
4 |
5 |
6 |
7 |
8 |
9 |
124 |
146 |
147 |
148 |
158 |
125 |
130 |
131 |
140 |
145 |
132 |
134 |
135 | See magrittr::%>% for details.
lhs %>% rhs136 | 137 | 138 | 139 |
63 |
64 |
118 |
119 |
120 |
121 |
122 |
123 |
166 |
167 |
168 |
169 |
170 |
171 |
172 |
173 |
174 |
--------------------------------------------------------------------------------
/inst/CITATION:
--------------------------------------------------------------------------------
1 | citHeader("To cite youtubecaption in publications use:")
2 |
3 | year = sub('.*(2[[:digit:]]{3})-.*', '\\1', meta$Date, perl = TRUE)
4 | vers = paste('R package version', meta$Version)
5 |
6 |
7 | citEntry(
8 | entry = "manual",
9 | title = paste('youtubecaption:', meta$Title),
10 | author = Filter(function(p) 'aut' %in% p$role, as.person(meta$Author)),
11 | year = year,
12 | note = vers,
13 | url = "https://CRAN.R-project.org/package=youtubecaption",
14 | textVersion = paste('JooYoung Seo & Soyoung Choi (', year, '). youtubecaption: ', meta$Title, '. ', vers, '.', sep = '')
15 | )
16 |
--------------------------------------------------------------------------------
/inst/NEWS:
--------------------------------------------------------------------------------
1 | # youtubecaption 1.0.0
2 |
3 | * Added a new argument `language` for `get_caption()` function (#1). You can now pass two-character language code; it is set to "en" (English) by default.
4 | * Cleaned up code indents for better readability.
5 |
6 |
7 | # youtubecaption 0.1.3
8 |
9 | * Fixed CITATION entries.
10 |
11 |
12 | # youtubecaption 0.1.2
13 |
14 | * `CITATION` file has been added.
15 |
16 |
17 | # youtubecaption 0.1.1
18 |
19 | * A critical bug that the third option `openxl` of `get_caption()` does not work properly has been resolved.
20 |
21 |
22 | # youtubecaption 0.1.0
23 |
24 | * Initial release.
25 |
--------------------------------------------------------------------------------
/man/get_caption.Rd:
--------------------------------------------------------------------------------
1 | % Generated by roxygen2: do not edit by hand
2 | % Please edit documentation in R/get_caption.R
3 | \name{get_caption}
4 | \alias{get_caption}
5 | \title{Obtaining YouTube video caption/subtitle in a tidy tibble form.}
6 | \usage{
7 | get_caption(
8 | url = NULL,
9 | language = "en",
10 | savexl = FALSE,
11 | openxl = FALSE,
12 | path = getwd()
13 | )
14 | }
15 | \arguments{
16 | \item{url}{A string value for a single YouTube video link URL. A typical form should start with "https://www.youtube.com/watch?v=" followed by a unique video ID.}
17 |
18 | \item{language}{two-character language code for the video URL. Set to "en" (English) by default. You can change this to fit with your needs (e.g., "ko" for Korean, "de" for German, etc.).}
19 |
20 | \item{savexl}{A logical value for determining whether or not to save the obtained tidy YouTube caption data as an Excel file. The default is FALSE which does not save it as a file. If set to TRUE, a file named "YouTube_caption_\code{videoID}.xlsx" is saved in your specified directory (the default is your current working directory).}
21 |
22 | \item{openxl}{A logical value for determining whether or not to open, if any, the saved YouTube_caption Excel file in your working directory. The default is FALSE. TRUE works only when the preceding argument (i.e., savexl) is set to TRUE.}
23 |
24 | \item{path}{A character vector of full path names; the default corresponds to the working directory, \link[base]{getwd}. Tilde expansion (see \link[base]{path.expand}) is performed. Missing values will be ignored.}
25 | }
26 | \value{
27 | tibble (advanced data.frame) object for a YouTube video caption will be returned.
28 | }
29 | \description{
30 | Use this function for downloading a desired YouTube video caption in a tidy tibble data_frame form and save it as an Excel file in your current working directory.
31 | }
32 | \details{
33 | get_caption
34 |
35 | See example below.
36 | }
37 | \examples{
38 | \donttest{
39 | library(youtubecaption)
40 | # Let's get the video caption out of Hadley Wickham's "You can't do data science in a GUI":
41 | url <- "https://www.youtube.com/watch?v=cpbtcsGE0OA"
42 | caption <- get_caption(url)
43 | caption
44 |
45 | # Save the caption as an Excel file and open it right it away
46 | ## Changing path to temp for the demonstration purpose only:
47 | get_caption(url = url, savexl = TRUE, openxl = TRUE, path = tempdir())
48 | }
49 |
50 | }
51 | \references{
52 | \url{https://pypi.org/project/youtube-transcript-api/}
53 | }
54 | \author{
55 | JooYoung Seo, \email{jooyoung@psu.edu}
56 |
57 | Soyoung Choi, \email{sxc940@psu.edu}
58 | }
59 | \keyword{get_caption}
60 |
--------------------------------------------------------------------------------
/man/pipe.Rd:
--------------------------------------------------------------------------------
1 | % Generated by roxygen2: do not edit by hand
2 | % Please edit documentation in R/utils-pipe.R
3 | \name{\%>\%}
4 | \alias{\%>\%}
5 | \title{Pipe operator}
6 | \usage{
7 | lhs \%>\% rhs
8 | }
9 | \description{
10 | See \code{magrittr::\link[magrittr]{\%>\%}} for details.
11 | }
12 | \keyword{internal}
13 |
--------------------------------------------------------------------------------
/man/youtubecaption-package.Rd:
--------------------------------------------------------------------------------
1 | % Generated by roxygen2: do not edit by hand
2 | % Please edit documentation in R/youtubecaption-package.R
3 | \docType{package}
4 | \name{youtubecaption-package}
5 | \alias{youtubecaption}
6 | \alias{youtubecaption-package}
7 | \title{youtubecaption: Downloading YouTube Subtitle Transcription in a Tidy Tibble Data Frame}
8 | \description{
9 | Although there exist some R packages tailored for YouTube API (e.g., 'tuber'), downloading YouTube video subtitle (i.e., caption) in a tidy form has never been a low-hanging fruit. Using 'youtube-transcript-api Python package' under the hood, this R package provides users with a convenient way of parsing and converting a desired YouTube caption into a handy 'tibble' data_frame object. Furthermore, users can easily save a desired YouTube caption data as a tidy Excel file without advanced programming background knowledge.
10 | }
11 | \seealso{
12 | Useful links:
13 | \itemize{
14 | \item \url{https://github.com/jooyoungseo/youtubecaption}
15 | \item Report bugs at \url{https://github.com/jooyoungseo/youtubecaption/issues}
16 | }
17 |
18 | }
19 | \author{
20 | \strong{Maintainer}: JooYoung Seo \email{jooyoung@psu.edu} (\href{https://orcid.org/0000-0002-4064-6012}{ORCID})
21 |
22 | Authors:
23 | \itemize{
24 | \item Soyoung Choi \email{sxc940@psu.edu} (\href{https://orcid.org/0000-0002-0998-3352}{ORCID})
25 | }
26 |
27 | }
28 | \keyword{internal}
29 |
--------------------------------------------------------------------------------
/vignettes/youtubecaption_vignette.Rmd:
--------------------------------------------------------------------------------
1 | ---
2 | title: "How to Use Youtubecaption"
3 | author: "JooYoung Seo"
4 | date: "`r Sys.Date()`"
5 | output: rmarkdown::html_vignette
6 | vignette: >
7 | %\VignetteIndexEntry{youtubecaption_vignette}
8 | %\VignetteEngine{knitr::rmarkdown}
9 | %\VignetteEncoding{UTF-8}
10 | ---
11 |
12 | ```{r, include = FALSE}
13 | knitr::opts_chunk$set(
14 | collapse = TRUE,
15 | comment = "#>",
16 | fig.path = "man/figures/README-",
17 | out.width = "100%"
18 | )
19 | ```
20 |
21 | # youtubecaption
22 |
23 |
24 | [](http://www.gnu.org/licenses/gpl-3.0)
25 | [](https://cran.r-project.org/package=youtubecaption)
26 | [](https://cranlogs.r-pkg.org/badges/grand-total/youtubecaption)
27 | [](https://travis-ci.org/jooyoungseo/youtubecaption)
28 | [](https://ci.appveyor.com/project/jooyoungseo/youtubecaption)
29 | [](https://codecov.io/gh/jooyoungseo/youtubecaption?branch=master)
30 |
31 |
32 | ## Motivation
33 |
34 | Although there exist some R packages tailored for YouTube API (e.g., 'tuber'), downloading YouTube video subtitle (i.e., caption) in a tidy form has never been a low-hanging fruit. Using 'youtube-transcript-api' Python package under the hood, this R package provides users with a convenient way of parsing and converting a desired YouTube caption into a handy tibble data_frame object. Furthermore, users can easily save a desired YouTube caption data as a tidy Excel file without advanced programming background knowledge.
35 |
36 | ## Installation
37 |
38 | ### Python Dependencies
39 |
40 | `youtubecaption` requires Anaconda Python environment on your system Path.
41 |
42 | If you have not installed Conda environment on your system, please [download and install Anaconda](https://www.anaconda.com/download/) (Python 3.6 or later is recommended).
43 |
44 | For this package, I have employed [**youtube-transcript-api**](https://pypi.org/project/youtube-transcript-api/) Python module into R using [**reticulate**](https://rstudio.github.io/reticulate/).
45 |
46 | ### R Package Installation
47 |
48 | ### Development Version
49 |
50 | You can install the latest development version as follows:
51 |
52 | ```{r, eval=FALSE}
53 | if(!require(remotes)) {
54 | install.packages("remotes")
55 | }
56 |
57 | remotes::install_github("jooyoungseo/youtubecaption")
58 | ```
59 |
60 | ### Stable Version
61 |
62 | You can install the released version of youtubecaption from [CRAN](https://CRAN.R-project.org) with:
63 |
64 | ```{r, eval=FALSE}
65 | install.packages('youtubecaption')
66 | ```
67 |
68 | ## Usage
69 |
70 | Please use `get_caption()` function after loading `youtubecaption` package like below:
71 |
72 | ```{r test, eval=FALSE}
73 | library(youtubecaption)
74 |
75 | # Let's get the video caption out of Hadley Wickham's "You can't do data science in a GUI":
76 | url <- "https://www.youtube.com/watch?v=cpbtcsGE0OA"
77 | caption <- get_caption(url)
78 | caption
79 |
80 | #> # A tibble: 1,420 x 5
81 | #> segment_id text start duration vid
82 | #>
124 |
153 |
154 |
155 |
165 |
125 |
145 |
146 |
147 |
152 |
126 |
129 |
130 |
131 | youtubecaption: Downloading YouTube Subtitle Transcription in a Tidy Tibble Data Frame
127 | Source:R/youtubecaption-package.R
128 | youtubecaption-package.Rd
132 |
134 |
135 |
136 |
137 | Although there exist some R packages tailored for YouTube API (e.g., 'tuber'), downloading YouTube video subtitle (i.e., caption) in a tidy form has never been a low-hanging fruit. Using 'youtube-transcript-api Python package' under the hood, this R package provides users with a convenient way of parsing and converting a desired YouTube caption into a handy 'tibble' data_frame object. Furthermore, users can easily save a desired YouTube caption data as a tidy Excel file without advanced programming background knowledge.
133 |See also
138 | 139 |Useful links:
-
140 |
- 141 |
Report bugs at https://github.com/jooyoungseo/youtubecaption/issues
142 |